RISE: Robust Imitation through Stochastic Encoding
This addresses safety challenges in robotic systems using offline imitation learning, but it is incremental as it builds on existing variational methods for robustness.
The paper tackles the problem of imitation learning failing to generalize in dynamic environments due to observation disturbances, and proposes RISE, a framework that encodes environment parameters into a variational latent space to improve robustness. The result shows improved safety robustness while maintaining goal-reaching performance on two robotic platforms compared to baselines.
Ensuring safety in robotic systems remains a fundamental challenge, especially when deploying offline policy-learning methods such as imitation learning in dynamic environments. Traditional behavior cloning (BC) often fails to generalize when deployed without fine-tuning as it does not account for disturbances in observations that arises in real-world, changing environments. To address this limitation, we propose RISE (Robust Imitation through Stochastic Encodings), a novel imitation-learning framework that explicitly addresses erroneous measurements of environment parameters into policy learning via a variational latent representation. Our framework encodes parameters such as obstacle state, orientation, and velocity into a smooth variational latent space to improve test time generalization. This enables an offline-trained policy to produce actions that are more robust to perceptual noise and environment uncertainty. We validate our approach on two robotic platforms, an autonomous ground vehicle and a Franka Emika Panda manipulator and demonstrate improved safety robustness while maintaining goal-reaching performance compared to baseline methods.